AI red teaming

Joe Lucas

doi:10.1117/12.3029883

10 June 2024 AI red teaming

Joe Lucas

Proceedings Volume 13054, Assurance and Security for AI-enabled Systems; 130540H (2024) https://doi.org/10.1117/12.3029883
Event: SPIE Defense + Commercial Sensing, 2024, National Harbor, Maryland, United States

Abstract

This is far more than just prompt injection and LLM jailbreaks. Apply a systematic lifecycle perspective to frame adversarial testing requirements and tactics for artificial intelligence (AI) systems. In this talk, we’ll explore why red teaming AI-enabled systems has some nuance that might not be covered during traditional testing and evaluation. We’ll discuss how to build AI red teaming capabilities, measure their performance and effectiveness, and explore the future of adversarial testing.

Conference Presentation

Citation Download Citation

Joe Lucas "AI red teaming", Proc. SPIE 13054, Assurance and Security for AI-enabled Systems, 130540H (10 June 2024); https://doi.org/10.1117/12.3029883

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available